Visualization of Focal Cues for Visuomotor Coordination by Gradient-based Methods: A Recurrent Neural Network Shifts the Attention Depending on Task Requirements

Hiroshi Ito, Kenjiro Yamamoto, Hiroki Mori, Shuki Goto, Tetsuya Ogata

研究成果: Conference contribution

抄録

For an autonomous robot to flexibly move in response to various tasks or environmental changes, an attention mechanism is required that is based on the robot's behavioral experience. In this paper, we visualize how attention is acquired inside a neural network learned using supervised learning and describe how to acquire a suitable representation for performing a task. Our experimental evaluation shows that the attention was automatically acquired for objects that are needed to perform tasks by learning the time-series of both vision and motor information rather than only vision information. By multimodal learning, the attention is robust against unlearned conditions which background changes or obstacles.

本文言語English
ホスト出版物のタイトルProceedings of the 2020 IEEE/SICE International Symposium on System Integration, SII 2020
出版社Institute of Electrical and Electronics Engineers Inc.
ページ188-194
ページ数7
ISBN(電子版)9781728166674
DOI
出版ステータスPublished - 2020 1
イベント2020 IEEE/SICE International Symposium on System Integration, SII 2020 - Honolulu, United States
継続期間: 2020 1 122020 1 15

出版物シリーズ

名前Proceedings of the 2020 IEEE/SICE International Symposium on System Integration, SII 2020

Conference

Conference2020 IEEE/SICE International Symposium on System Integration, SII 2020
国/地域United States
CityHonolulu
Period20/1/1220/1/15

ASJC Scopus subject areas

  • 人工知能
  • コンピュータ サイエンスの応用
  • 生体医工学
  • 制御およびシステム工学
  • 安全性、リスク、信頼性、品質管理
  • 制御と最適化
  • 器械工学

フィンガープリント

「Visualization of Focal Cues for Visuomotor Coordination by Gradient-based Methods: A Recurrent Neural Network Shifts the Attention Depending on Task Requirements」の研究トピックを掘り下げます。これらがまとまってユニークなフィンガープリントを構成します。

引用スタイル